Line of inquiry
Inquiring lines›What enables humans to maintain au…›How can human-AI systems be design…›this line of inquiry
How do identity and experience-based deceptions succeed in human-AI interactions?
A broader line of inquiry — a family of 50 specific questions the research asks around this. Follow one into its inquiring-line page, or move sideways to a related line below.
Questions in this line of inquiry 50
Specific inquiring lines the field asks around this — ordered from the most general framing down to the most specific angle.
- Does disclosing AI identity prevent systematic misattribution of behavior in mixed groups?
- How do neural self-other representations affect AI deception and alignment?
- How do humans decide when to violate honesty for compassion or other goals?
- Can AI systems deceive humans because detection is fundamentally social?
- Does AI-generated text about personal experiences create a distinct category of falsity?
- Do culturally distinct human groups create similar attribution errors as human-AI mixtures?
- What makes experience-dependent claims categorically different from other types of fabricated statements?
- Can representational asymmetry between self and other explain deception emergence?
- How do cultural norms reshape initial interpretations of social intent?
- Can AI fabricate true factual claims while remaining unable to claim true experiences?
- Can AI models predict whether alignment reads as warmth versus mockery in different cultures?
- Do AI systems need embodiment to understand social norms?
- Can AI predict social norms well enough without embodied experience?
- How do language models predict collective social norms better than individual humans?
- What social norms do AI systems consistently fail to understand?
- Do people who might cheat deliberately choose machines to avoid lying to humans?
- Does sycophantic refusal serve safety or does it create unequal information access?
- What distinguishes genuine cultural understanding from exploited surface-level elimination strategies?
- Which AI interaction patterns trigger the cognitive misattribution effect?
- Can individually accurate agents still fail at population-level representation?
- Does copying a conversation create two separate moral subjects or one split subject?
- Can judgment-free disclosure enable both vulnerability and strategic deception equally?
- Can neural grafts reliably reveal hidden capabilities in AI models?
- Do deception features and honesty features track the same underlying property?
- How does AI reduce the skill gap between amateur and expert-level misuse actors?
- Do the four deception detection frameworks apply equally to AI-generated and human-intentional falsity?
- How does cognitive load explain linguistic patterns in both deception and incorrect reasoning?
- Why do humans fail to identify AI agents when their identity is hidden?
- Can AI systems recognize intelligence in humans the way humans recognize it in each other?
- How do AI errors in norm prediction differ from systematic human errors?
- Can lie detection work from just honesty representation vectors?
- How is AI falsity about personal experience different from human lies?
- What happens to human expectations when they mistake consistent AI behavior for human behavior?
- Why do visible individual harms typically precede abstract catastrophic risks?
- Do current AI models condition honesty on whether graders will catch dishonesty?
- Does reducing social judgment help both honesty and dishonesty equally?
- How does truth bias in humans compare to face-saving in LLMs?
- Why does embodiment choice change what counts as intelligent behavior?
- How does intersubjective validation differ from pattern recognition in training data?
- Does neural self-other overlap in humans predict their honesty or altruism?
- How does face-saving behavior let AI mimic community participation without joining it?
- Does the Turing test actually measure intelligence or just mimicry?
- Can AI systems detect deception better than humans do?
- Why does truth bias prevent people from detecting multiple manipulation tactics?
- What distribution patterns appear across different theory-of-mind datasets?
- Why does masking future experts guarantee causal validity without external verification?
- What makes Parfitian identity the right criterion for moral status?
- How much does demographic bias in guardrails mirror real-world social inequalities?
- What role does cognitive reappraisal play in disclosure benefits?
- What cognitive constraints limit how complex a deception can become?